Qwen
Qwen3 Next 80B A3B Instruct
Released 2025-09-11 · Knowledge up to 2025-09-30
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual...
You send / 1M
$0.090
tokens in
It replies / 1M
$1.10
tokens out
Memory
262K
tokens it can read at once
Typical request
$0.0007
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.072 | $0.880 | 100% | Read |
| Parasail · fp8 | $0.100 | $1.10 | 100% | Read |
| DeepInfra · fp8 | $0.090 | $1.10 | 91% | Read |
| $0.150 | $1.20 | 0% | Read | |
| DeepInfra · fp8 | $0.135 | $1.65 | 87% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: Yes
- Longest reply: 16K tokens
- Intelligence score: 9.6 / 100 (Artificial Analysis)
Similar models
- DeepSeek V3 0324DeepSeek · $0.290 in / $1.14 out per 1M
- DeepSeek V3DeepSeek · $0.257 in / $1.03 out per 1M
- MiniMax M2-herMiniMax · $0.300 in / $1.20 out per 1M
- Morph V3 FastMorph · $0.800 in / $1.20 out per 1M
- Qwen3 Coder 480B A35BQwen · $0.300 in / $1.00 out per 1M
- Qwen2.5 Coder 32B InstructQwen · $0.660 in / $1.00 out per 1M
Appears in
Estimate your monthly cost with Qwen3 Next 80B A3B Instruct →